Update README.md
Browse files
README.md
CHANGED
|
@@ -8,7 +8,7 @@ inference: false
|
|
| 8 |
|
| 9 |
Models better suited for High-Resolution Image Synthesis. The main model (doohickey/doohickey-mega) has been finetuned from [runwayml/stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) near a resolution of 768x768 (suggested method of generating from model is with [Doohickey](https://colab.research.google.com/github/aicrumb/doohickey/blob/main/Doohickey_Diffusion.ipynb)).
|
| 10 |
|
| 11 |
-
This is a version of Stable Diffusion finetuned to use [laion/CLIP-ViT-L-14-laion2B-s32B-b82K](https://huggingface.co/laion/CLIP-ViT-L-14-laion2B-s32B-b82K) instead of the stock openai clip model
|
| 12 |
|
| 13 |
_Limitations and Biases from Stable Diffusion also apply to this model._
|
| 14 |
|
|
|
|
| 8 |
|
| 9 |
Models better suited for High-Resolution Image Synthesis. The main model (doohickey/doohickey-mega) has been finetuned from [runwayml/stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) near a resolution of 768x768 (suggested method of generating from model is with [Doohickey](https://colab.research.google.com/github/aicrumb/doohickey/blob/main/Doohickey_Diffusion.ipynb)).
|
| 10 |
|
| 11 |
+
This is a version of Stable Diffusion finetuned to use [laion/CLIP-ViT-L-14-laion2B-s32B-b82K](https://huggingface.co/laion/CLIP-ViT-L-14-laion2B-s32B-b82K) instead of the stock openai clip model. While doohickey-mega finetuned the CLIP model as well, this ckpt was finetuned without the CLIP model being trained. In total 6000 steps.
|
| 12 |
|
| 13 |
_Limitations and Biases from Stable Diffusion also apply to this model._
|
| 14 |
|